Recognise and Classify handwritten digits from the MNIST Database using kNN Algorithm

The MNIST Database contains around 70,000 images of handwritten digits. 60,000 of these images are fed to the algorithm, along with their correct corresponding digit values.

Subsequent to this, any image from the remaining 10,000 can be input as a test case. Using the conventional k-Nearest Neighbours Algorithm, the model identifies the digit in the image.

This prediction is compared with the acutal correct value. Also the value of k (i.e. number of nearest neighbours to be considered), can be set to an appropriate value so as to have optimal accuracy, while simultaneously having a small execution time.